Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns starting with the letter "A"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'A' as a standalone character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     optics
    -0.68
    enegger
    -0.64
     upstairs
    -0.61
     negatives
    -0.58
     enclosed
    -0.57
     outl
    -0.57
     IPS
    -0.56
     accuracy
    -0.55
     intended
    -0.55
     overt
    -0.54
    POSITIVE LOGITS
    cknow
    1.27
    cknowled
    1.23
    perture
    1.21
    ussie
    1.19
    verages
    1.17
    uctions
    1.11
    ileen
    1.08
    HA
    1.05
    BILITIES
    1.04
    UG
    1.02
    Act Density 0.072%

    No Known Activations